© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48910
    Prev
    Next
    INDEX
    Explanations

    news feeds and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inex
    -0.88
     AssemblyCulture
    -0.86
     دارند
    -0.86
     reap
    -0.85
    文学
    -0.82
    geblich
    -0.82
    দ্
    -0.81
    Pren
    -0.81
     prés
    -0.79
     impre
    -0.79
    POSITIVE LOGITS
     feed
    1.13
     IFTTT
    1.11
    feed
    0.96
     Source
    0.93
     source
    0.91
     Feed
    0.87
    iress
    0.86
     ★
    0.84
     news
    0.83
     HAPPENED
    0.82
    Activations Density 0.103%

    No Known Activations